A method and apparatus for improving the management of cash and liquidity of an organization utilizing a plurality of currency accounts is described. The improvements optimize the interest earnings for the cash balances in each currency account, and minimizes the expenses related to funding the currency accounts. Machine learning techniques are incorporated to forecast payments, receipts, interest rates and currency exchange rates, and then cash is transferred or borrowed or loaned to fund the payments and utilize available cash.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The cash management method of claim 1 wherein the machine learning algorithm is Random Forest.
3. The cash management method of claim 1 wherein the machine learning algorithm includes a minimum recall parameter and a minimum precision parameter and repeats a process of learning a rule for a target class and removes all target class examples covered by the rule until no role can be generated to satisfy the minimum recall parameter and the minimum precision parameter.
4. The cash management method of claim 1 wherein the given past date range is user configurable.
5. The cash management method of claim 1 further comprising modifying the forecast of the payments by incorporating actual planned payments.
6. The cash management method of claim 1 further comprising modifying the forecast of the receipts by incorporating actual planned receipts.
7. The cash management method of claim 1 wherein each currency account further comprises currency accounts for a plurality of subsidiaries.
8. The cash management method of claim 1 wherein the execution of the instructions to make the payments and the cash transfers are made by transferring one or more files to a plurality of banking rails.
9. The cash management method of claim 8 wherein the bank rate information is retrieved from the one or more banks over the banking rails.
10. The cash management method of claim 1 wherein the bank rate information comprises interest rates, foreign exchange rates, and money transfer costs.
12. The method of claim 11 wherein the machine learning algorithm is K-means.
13. The method of claim 11 wherein the machine learning algorithm is Random Forest.
14. The method of claim 11 wherein the given past date range is user configurable.
15. The method of claim 11 further comprising modifying the forecast of the payments by incorporating actual planned payments.
16. The method of claim 11 further comprising modifying the forecast of the receipts by incorporating actual planned receipts.
17. The method of claim 11 wherein each currency account further comprises currency accounts for a plurality of subsidiaries.
18. The method of claim 11 wherein the execution of the instructions to make the payments and the cash transfers are made by transferring one or more files to a plurality of banking rails.
19. The method of claim 18 wherein the bank rate information is retrieved from the one or more banks over the banking rails.
20. The method of claim 11 wherein the bank rate information comprises interest rates, foreign exchange rates, and money transfer costs.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
September 2, 2022
May 28, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.